January 2026

arXiv:2601.15014v1 Announce Type: new Abstract: We study in-context learning for nonparametric regression with $alpha$-H”older smooth regression functions, for some $alpha>0$. We prove that, with $n$ in-context examples and $d$-dimensional regression covariates, a pretrained transformer with $Theta(log n)$ parameters and $Omegabigl(n^{2alpha/(2alpha+d)}log^3 nbigr)$ pretraining sequences can achieve the minimax-optimal rate of convergence $Obigl(n^{-2alpha/(2alpha+d)}bigr)$ in mean squared error. Our result requires substantially fewer transformer parameters and pretraining sequences than previous results in the literature. This is achieved by showing that transformers […]

Ver mais

arXiv:2601.14631v1 Announce Type: new Abstract: This paper presents a semi-supervised learning framework for Gaussian mixture modelling under a Missing at Random (MAR) mechanism. The method explicitly parameterizes the missingness mechanism by modelling the probability of missingness as a function of classification uncertainty. To quantify classification uncertainty, we introduce margin confidence and incorporate the Aranda Ordaz (AO) link function to flexibly capture the asymmetric relationships between uncertainty and missing probability. Based on this formulation, we develop an efficient Expectation […]

Ver mais

arXiv:2601.14609v1 Announce Type: new Abstract: Privacy-preserving model co-training in medical research is often hindered by server-dependent architectures incompatible with protected hospital data systems and by the predominant focus on relative effect measures (hazard ratios) which lack clinical interpretability for absolute survival risk assessment. We propose FedRD, a communication-efficient framework for federated risk difference estimation in distributed survival data. Unlike typical federated learning frameworks (e.g., FedAvg) that require persistent server connections and extensive iterative communication, FedRD is server-independent with […]

Ver mais

arXiv:2601.14515v1 Announce Type: new Abstract: Laplace learning is a semi-supervised method, a solution for finding missing labels from a partially labeled dataset utilizing the geometry given by the unlabeled data points. The method minimizes a Dirichlet energy defined on a (discrete) graph constructed from the full dataset. In finite dimensions the asymptotics in the large (unlabeled) data limit are well understood with convergence from the graph setting to a continuum Sobolev semi-norm weighted by the Lebesgue density of […]

Ver mais

arXiv:2601.14430v1 Announce Type: new Abstract: Controlling generative models is computationally expensive. This is because optimal alignment with a reward function–whether via inference-time steering or fine-tuning–requires estimating the value function. This task demands access to the conditional posterior $p_{1|t}(x_1|x_t)$, the distribution of clean data $x_1$ consistent with an intermediate state $x_t$, a requirement that typically compels methods to resort to costly trajectory simulations. To address this bottleneck, we introduce Meta Flow Maps (MFMs), a framework extending consistency models and […]

Ver mais

arXiv:2601.14510v1 Announce Type: new Abstract: Gaussian Splatting (GS) has recently emerged as a state-of-the-art representation for radiance fields, combining real-time rendering with high visual fidelity. However, GS models require storing millions of parameters, leading to large file sizes that impair their use in practical multimedia systems. To address this limitation, this paper introduces GS Image-based Compression (GSICO), a novel GS codec that efficiently compresses pre-trained GS models while preserving perceptual fidelity. The core contribution lies in a mapping […]

Ver mais

arXiv:2601.14508v1 Announce Type: new Abstract: Super-time-stepping (STS) methods provide an attractive approach for enabling explicit time integration of parabolic operators, particularly in large-scale, higher-dimensional kinetic simulations where fully implicit schemes are impractical. In this work, we present an explicit STS framework tailored for diffusion operators in gyrokinetic models, motivated by the fact that constructing and storing a Jacobian is often infeasible due to strong nonlocal couplings, high dimensionality, and memory constraints. We investigate the performance of several STS […]

Ver mais

arXiv:2601.14506v1 Announce Type: new Abstract: The popularization of AI chatbot usage globally has created opportunities for research into their benefits and drawbacks, especially for students using AI assistants for coursework support. This paper asks: how do LLMs perceive the intellectual capabilities of student profiles from intersecting marginalized identities across different cultural contexts? We conduct one of the first large-scale intersectional analyses on LLM explanation quality for Indian and American undergraduate profiles preparing for engineering entrance examinations. By constructing […]

Ver mais

arXiv:2601.14505v1 Announce Type: new Abstract: In the network security domain, due to practical issues — including imbalanced data and heterogeneous legitimate network traffic — adversarial attacks in machine learning-based NIDSs have been viewed as attack packets misclassified as benign. Due to this prevailing belief, the possibility of (maliciously) perturbed benign packets being misclassified as attack has been largely ignored. In this paper, we demonstrate that this is not only theoretically possible, but also a particular threat to NIDS. […]

Ver mais

arXiv:2601.14503v1 Announce Type: new Abstract: Recent European efforts around digital identity — the EUDI regulation and its OpenID architecture — aim high, but start from a narrow and ill-defined conceptualization of authentication. Based on a broader, more grounded understanding of the term, in we identify several issues in the design of OpenID4VCI and OpenID4VP: insecure practices, static, and subject-bound credential types, and a limited query language restrict their application to classic scenarios of credential exchange — already supported […]

Ver mais